Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0742

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0742
File size: 4,475 Bytes 
96ff48c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.9354666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0742/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.208075523376465,
      "learning_rate": 4.447781114447781e-05,
      "loss": 0.716,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.3474268317222595,
      "eval_runtime": 10.919,
      "eval_samples_per_second": 343.438,
      "eval_steps_per_second": 5.403,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.435003638267517,
      "learning_rate": 3.892225558892226e-05,
      "loss": 0.1997,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.36249658465385437,
      "eval_runtime": 11.2447,
      "eval_samples_per_second": 333.491,
      "eval_steps_per_second": 5.247,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.812775135040283,
      "learning_rate": 3.33667000333667e-05,
      "loss": 0.0997,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.3331863284111023,
      "eval_runtime": 11.5947,
      "eval_samples_per_second": 323.425,
      "eval_steps_per_second": 5.089,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 2.782782782782783e-05,
      "loss": 0.0572,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.39966559410095215,
      "eval_runtime": 10.9877,
      "eval_samples_per_second": 341.29,
      "eval_steps_per_second": 5.37,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.00248286547139287,
      "learning_rate": 2.2272272272272273e-05,
      "loss": 0.0287,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9197333333333333,
      "eval_loss": 0.3105076849460602,
      "eval_runtime": 11.1993,
      "eval_samples_per_second": 334.841,
      "eval_steps_per_second": 5.268,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.21770690381526947,
      "learning_rate": 1.6716716716716717e-05,
      "loss": 0.0103,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.3289019465446472,
      "eval_runtime": 11.236,
      "eval_samples_per_second": 333.748,
      "eval_steps_per_second": 5.251,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.001557586365379393,
      "learning_rate": 1.1161161161161162e-05,
      "loss": 0.0029,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9269333333333334,
      "eval_loss": 0.3126938045024872,
      "eval_runtime": 11.5119,
      "eval_samples_per_second": 325.751,
      "eval_steps_per_second": 5.125,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4655797779560089,
      "learning_rate": 5.605605605605606e-06,
      "loss": 0.0012,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.30061355233192444,
      "eval_runtime": 10.9602,
      "eval_samples_per_second": 342.148,
      "eval_steps_per_second": 5.383,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.00048774181050248444,
      "learning_rate": 5.005005005005005e-08,
      "loss": 0.0007,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9354666666666667,
      "eval_loss": 0.2860882878303528,
      "eval_runtime": 10.9385,
      "eval_samples_per_second": 342.825,
      "eval_steps_per_second": 5.394,
      "step": 2997
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}